Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4496 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.8414. Min Act: -0.1700
Data Index: 4921312 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.7164. Min Act: -0.1700
Data Index: 2619763 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.7789. Min Act: -0.1700
Data Index: 7839857 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.5914. Min Act: -0.1700
Data Index: 1065023 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.5914. Min Act: -0.1700
Data Index: 3628169 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.5914. Min Act: -0.1700
Data Index: 1270268 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.5914. Min Act: -0.1700
Data Index: 717614 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.5289. Min Act: -0.1700
Data Index: 1785546 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4976. Min Act: -0.1700
Data Index: 5477666 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4976. Min Act: -0.1700
Data Index: 5809004 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4976. Min Act: -0.1700
Data Index: 6691018 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4976. Min Act: -0.1700
Data Index: 6690070 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.5289. Min Act: -0.1700
Data Index: 5189048 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4664. Min Act: -0.1700
Data Index: 6401857 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4664. Min Act: -0.1700
Data Index: 1879711 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4664. Min Act: -0.1700
Data Index: 3648736 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4664. Min Act: -0.1700
Data Index: 1060680 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4039. Min Act: -0.1700
Data Index: 3810877 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4351. Min Act: -0.1700
Data Index: 2885959 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8414. Min Range: -7.8414
Max Act: 7.4351. Min Act: -0.1700
Data Index: 7438664 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19